On the convergence of Jacobi-type algorithms for Independent Component Analysis - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

On the convergence of Jacobi-type algorithms for Independent Component Analysis

Résumé

Jacobi-type algorithms for simultaneous approximate diagonalization of real (or complex) symmetric tensors have been widely used in independent component analysis (ICA) because of their good performance. One natural way of choosing the index pairs in Jacobitype algorithms is the classical cyclic ordering, while the other way is based on the Riemannian gradient in each iteration. In this paper, we mainly review in an accessible manner our recent results in a series of papers about weak and global convergence of these Jacobitype algorithms. These results are mainly based on the Lojasiewicz gradient inequality.

Dates et versions

hal-02994725 , version 1 (08-11-2020)

Identifiants

Citer

Jianze Li, Konstantin Usevich, Pierre Comon. On the convergence of Jacobi-type algorithms for Independent Component Analysis. SAM 2020 - 11th Sensor Array and Multichannel Signal Processing Workshop, Jun 2020, Hangzhou (virtual), China. ⟨10.1109/SAM48682.2020.9104331⟩. ⟨hal-02994725⟩
48 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More